@inproceedings{hu-etal-2024-unified,
title = "A Unified Generative Framework for Bilingual Euphemism Detection and Identification",
author = "Hu, Yuxue and
Li, Junsong and
Wang, Tongguan and
Su, Dongyu and
Su, Guixin and
Sha, Ying",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.403",
doi = "10.18653/v1/2024.findings-acl.403",
pages = "6753--6766",
abstract = "Various euphemisms are emerging in social networks, attracting widespread attention from the natural language processing community. However, existing euphemism datasets are only domain-specific or language-specific. In addition, existing approaches to the study of euphemisms are one-sided. Either only the euphemism detection task or only the euphemism identification task is accomplished, lacking a unified framework. To this end, we construct a large-scale Bilingual Multi-category dataset of Euphemisms named BME, which covers a total of 12 categories for two languages, English and Chinese. Then, we first propose a unified generative model to Jointly conduct the tasks of bilingual Euphemism Detection and Identification named JointEDI. By comparing with LLMs and human evaluation, we demonstrate the effectiveness of the proposed JointEDI and the feasibility of unifying euphemism detection and euphemism identification tasks. Moreover, the BME dataset also provides a new reference standard for euphemism detection and euphemism identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2024-unified">
<titleInfo>
<title>A Unified Generative Framework for Bilingual Euphemism Detection and Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxue</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junsong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tongguan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guixin</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Sha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Various euphemisms are emerging in social networks, attracting widespread attention from the natural language processing community. However, existing euphemism datasets are only domain-specific or language-specific. In addition, existing approaches to the study of euphemisms are one-sided. Either only the euphemism detection task or only the euphemism identification task is accomplished, lacking a unified framework. To this end, we construct a large-scale Bilingual Multi-category dataset of Euphemisms named BME, which covers a total of 12 categories for two languages, English and Chinese. Then, we first propose a unified generative model to Jointly conduct the tasks of bilingual Euphemism Detection and Identification named JointEDI. By comparing with LLMs and human evaluation, we demonstrate the effectiveness of the proposed JointEDI and the feasibility of unifying euphemism detection and euphemism identification tasks. Moreover, the BME dataset also provides a new reference standard for euphemism detection and euphemism identification.</abstract>
<identifier type="citekey">hu-etal-2024-unified</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.403</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.403</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>6753</start>
<end>6766</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Generative Framework for Bilingual Euphemism Detection and Identification
%A Hu, Yuxue
%A Li, Junsong
%A Wang, Tongguan
%A Su, Dongyu
%A Su, Guixin
%A Sha, Ying
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F hu-etal-2024-unified
%X Various euphemisms are emerging in social networks, attracting widespread attention from the natural language processing community. However, existing euphemism datasets are only domain-specific or language-specific. In addition, existing approaches to the study of euphemisms are one-sided. Either only the euphemism detection task or only the euphemism identification task is accomplished, lacking a unified framework. To this end, we construct a large-scale Bilingual Multi-category dataset of Euphemisms named BME, which covers a total of 12 categories for two languages, English and Chinese. Then, we first propose a unified generative model to Jointly conduct the tasks of bilingual Euphemism Detection and Identification named JointEDI. By comparing with LLMs and human evaluation, we demonstrate the effectiveness of the proposed JointEDI and the feasibility of unifying euphemism detection and euphemism identification tasks. Moreover, the BME dataset also provides a new reference standard for euphemism detection and euphemism identification.
%R 10.18653/v1/2024.findings-acl.403
%U https://aclanthology.org/2024.findings-acl.403
%U https://doi.org/10.18653/v1/2024.findings-acl.403
%P 6753-6766
Markdown (Informal)
[A Unified Generative Framework for Bilingual Euphemism Detection and Identification](https://aclanthology.org/2024.findings-acl.403) (Hu et al., Findings 2024)
ACL